© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64540
    Prev
    Next
    INDEX
    Explanations

    isotopes and tracers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gments
    -0.07
     rogh
    -0.07
    brica
    -0.07
    volt
    -0.07
    PRIVATE
    -0.07
     onwe
    -0.07
    ativ
    -0.07
     musical
    -0.07
     Islamic
    -0.07
    mett
    -0.07
    POSITIVE LOGITS
     tracer
    0.15
    _tracking
    0.12
     tracking
    0.11
    Tracking
    0.11
     trac
    0.11
    .trace
    0.10
    Tracer
    0.10
     tracing
    0.10
    (trace
    0.10
    Tracing
    0.09
    Activations Density 0.005%

    No Known Activations